View All Items

Title: An artificial neural network architecture for interpolation, function approximation, time series modeling and control applications.
Creator: Luebbers, Paul Glenn., Florida Atlantic University, Pandya, Abhijit S., Sudhakar, Raghavan, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: A new artificial neural network architecture called Power Net (PWRNET) and Orthogonal Power Net (OPWRNET) has been developed. Based on the Taylor series expansion of the hyperbolic tangent function, this novel architecture can approximate multi-input multi-layer artificial networks, while requiring only a single layer of hidden nodes. This allows a compact network representation with only one layer of hidden layer weights. The resulting trained network can be expressed as a polynomial...
Show moreA new artificial neural network architecture called Power Net (PWRNET) and Orthogonal Power Net (OPWRNET) has been developed. Based on the Taylor series expansion of the hyperbolic tangent function, this novel architecture can approximate multi-input multi-layer artificial networks, while requiring only a single layer of hidden nodes. This allows a compact network representation with only one layer of hidden layer weights. The resulting trained network can be expressed as a polynomial function of the input nodes. Applications which cannot be implemented with conventional artificial neural networks, due to their intractable nature, can be developed with these network architectures. The degree of nonlinearity of the network can be directly controlled by adjusting the number of hidden layer nodes, thus avoiding problems of over-fitting which restrict generalization. The learning algorithm used for adapting the network is the familiar error back propagation training algorithm. Other learning algorithms may be applied and since only one hidden layer is to be trained, the training performance of the network is expected to be comparable to or better than conventional multi-layer feed forward networks. The new architecture is explored by applying OPWRNET to classification, function approximation and interpolation problems. These applications show that the OPWRNET has comparable performance to multi-layer perceptrons. The OPWRNET was also applied to the prediction of noisy time series and the identification of nonlinear systems. The resulting trained networks, for system identification tasks, can be expressed directly as discrete nonlinear recursive polynomials. This characteristic was exploited in the development of two new neural network based nonlinear control algorithms, the Linearized Self-Tuning Controller (LSTC) and a variation of a Neural Adaptive Controller (NAC). These control algorithms are compared to a linear self-tuning controller and an artificial neural network based Inverse Model Controller. The advantages of these new controllers are discussed.
Show less
Date Issued: 1994
PURL: http://purl.flvc.org/fcla/dt/12357
Subject Headings: Neural networks (Computer science)
Format: Document (PDF)

Title: Learning in connectionist networks using the Alopex algorithm.
Creator: Venugopal, Kootala Pattath., Florida Atlantic University, Pandya, Abhijit S., Sudhakar, Raghavan, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: The Alopex algorithm is presented as a universal learning algorithm for connectionist models. It is shown that the Alopex procedure could be used efficiently as a supervised learning algorithm for such models. The algorithm is demonstrated successfully on a variety of network architectures. Such architectures include multilayer perceptrons, time-delay models, asymmetric, fully recurrent networks and memory neuron networks. The learning performance as well as the generation capability of the...
Show moreThe Alopex algorithm is presented as a universal learning algorithm for connectionist models. It is shown that the Alopex procedure could be used efficiently as a supervised learning algorithm for such models. The algorithm is demonstrated successfully on a variety of network architectures. Such architectures include multilayer perceptrons, time-delay models, asymmetric, fully recurrent networks and memory neuron networks. The learning performance as well as the generation capability of the Alopex algorithm are compared with those of the backpropagation procedure, concerning a number of benchmark problems, and it is shown that the Alopex has specific advantages over the backpropagation. Two new architectures (gain layer schemes) are proposed for the on-line, direct adaptive control of dynamical systems using neural networks. The proposed schemes are shown to provide better dynamic response and tracking characteristics, than the other existing direct control schemes. A velocity reference scheme is introduced to improve the dynamic response of on-line learning controllers. The proposed learning algorithm and architectures are studied on three practical problems; (i) Classification of handwritten digits using Fourier Descriptors; (ii) Recognition of underwater targets from sonar returns, considering temporal dependencies of consecutive returns and (iii) On-line learning control of autonomous underwater vehicles, starting with random initial conditions. Detailed studies are conducted on the learning control applications. Effect of the network learning rate on the tracking performance and dynamic response of the system are investigated. Also, the ability of the neural network controllers to adapt to slow and sudden varying parameter disturbances and measurement noise is studied in detail.
Show less
Date Issued: 1993
PURL: http://purl.flvc.org/fcla/dt/12325
Subject Headings: Computer algorithms, Computer networks, Neural networks (Computer science), Machine learning
Format: Document (PDF)

Title: COMPARISON OF PRE-TRAINED CONVOLUTIONAL NEURAL NETWORK PERFORMANCE ON GLIOMA CLASSIFICATION.
Creator: Andrews, Whitney Angelica Johanna, Furht, Borko, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Gliomas are an aggressive class of brain tumors that are associated with a better prognosis at a lower grade level. Effective differentiation and classification are imperative for early treatment. MRI scans are a popular medical imaging modality to detect and diagnosis brain tumors due to its capability to non-invasively highlight the tumor region. With the rise of deep learning, researchers have used convolution neural networks for classification purposes in this domain, specifically pre...
Show moreGliomas are an aggressive class of brain tumors that are associated with a better prognosis at a lower grade level. Effective differentiation and classification are imperative for early treatment. MRI scans are a popular medical imaging modality to detect and diagnosis brain tumors due to its capability to non-invasively highlight the tumor region. With the rise of deep learning, researchers have used convolution neural networks for classification purposes in this domain, specifically pre-trained networks to reduce computational costs. However, with various MRI modalities, MRI machines, and poor image scan quality cause different network structures to have different performance metrics. Each pre-trained network is designed with a different structure that allows robust results given specific problem conditions. This thesis aims to cover the gap in the literature to compare the performance of popular pre-trained networks on a controlled dataset that is different than the network trained domain.
Show less
Date Issued: 2020
PURL: http://purl.flvc.org/fau/fd/FA00013450
Subject Headings: Gliomas, Neural networks (Computer science), Deep Learning, Convolutional neural networks
Format: Document (PDF)

Title: Maximum entropy-based optimization of artificial neural networks: An application to ATM telecommunication parameter predictions.
Creator: Sundaram, Karthik., Florida Atlantic University, De Groff, Dolores F., Neelakanta, Perambur S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: This thesis addresses studies on cost-functions developed on the basis of maximum entropy principle, for applications in artificial neural network (ANN) optimization endeavors. The maximization of entropy refers to maximizing Shannon information pertinent to the difference in the output and the teacher value of an ANN. Apart from the Shannon format of the negative entropy formulation a set of Csiszar family functions are also considered. The error-measures obtained, via these maximum entropy...
Show moreThis thesis addresses studies on cost-functions developed on the basis of maximum entropy principle, for applications in artificial neural network (ANN) optimization endeavors. The maximization of entropy refers to maximizing Shannon information pertinent to the difference in the output and the teacher value of an ANN. Apart from the Shannon format of the negative entropy formulation a set of Csiszar family functions are also considered. The error-measures obtained, via these maximum entropy formulations are adopted as cost-functions in the training and prediction schedules of a test perceptron. A comparative study is done on the performance of these cost-functions in facilitating the test network towards optimization so as to predict a standard teacher function sin (.). The study is also extended to predict a parameter (such as cell delay variation) in a practical ATM telecommunication system. Concluding remarks and scope for an extended study are also indicated.
Show less
Date Issued: 1999
PURL: http://purl.flvc.org/fcla/dt/15660
Subject Headings: Neural network (Computer science), Asynchronous transfer mode
Format: Document (PDF)

Title: BEHAVIORAL ANALYSIS OF DEEP CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE CLASSIFICATION.
Creator: Clark, James Alex, Barenholtz, Elan, Florida Atlantic University, Center for Complex Systems and Brain Sciences, Charles E. Schmidt College of Science
Abstract/Description: Within Deep CNNs there is great excitement over breakthroughs in network performance on benchmark datasets such as ImageNet. Around the world competitive teams work on new ways to innovate and modify existing networks, or create new ones that can reach higher and higher accuracy levels. We believe that this important research must be supplemented with research into the computational dynamics of the networks themselves. We present research into network behavior as it is affected by: variations...
Show moreWithin Deep CNNs there is great excitement over breakthroughs in network performance on benchmark datasets such as ImageNet. Around the world competitive teams work on new ways to innovate and modify existing networks, or create new ones that can reach higher and higher accuracy levels. We believe that this important research must be supplemented with research into the computational dynamics of the networks themselves. We present research into network behavior as it is affected by: variations in the number of filters per layer, pruning filters during and after training, collapsing the weight space of the trained network using a basic quantization, and the effect of Image Size and Input Layer Stride on training time and test accuracy. We provide insights into how the total number of updatable parameters can affect training time and accuracy, and how “time per epoch” and “number of epochs” affect network training time. We conclude with statistically significant models that allow us to predict training time as a function of total number of updatable parameters in the network.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00013940
Subject Headings: Neural networks (Computer science), Image processing
Format: Document (PDF)

Title: A BCU scalable sensory acquisition system for EEG embedded applications.
Creator: Fathalla, Sherif S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Electroencephalogram (EEG) Recording has been through a lot of changes and modification since it was first introduced in 1929 due to rising technologies and signal processing advancements. The EEG Data acquisition stage is the first and most valuable component in any EEG recording System, it has the role of gathering and conditioning its input and outputting reliable data to be effectively analyzed and studied by digital signal processors using sophisticated and advanced algorithms which help...
Show moreElectroencephalogram (EEG) Recording has been through a lot of changes and modification since it was first introduced in 1929 due to rising technologies and signal processing advancements. The EEG Data acquisition stage is the first and most valuable component in any EEG recording System, it has the role of gathering and conditioning its input and outputting reliable data to be effectively analyzed and studied by digital signal processors using sophisticated and advanced algorithms which help in numerous medical and consumer applications. We have designed a low noise low power EEG data acquisition system that can be set to act as a standalone mobile EEG data processing unit providing data preprocessing functions; it can also be a very reliable high speed data acquisition interface to an EEG processing unit.
Show less
Date Issued: 2010
PURL: http://purl.flvc.org/FAU/3164095
Subject Headings: Brain-computer interfaces, Computational neuroscience, Neural networks (Computer science)
Format: Document (PDF)

Title: Detection of change-prone telecommunications software modules.
Creator: Weir, Ronald Eugene., Florida Atlantic University, Khoshgoftaar, Taghi M., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Accurately classifying the quality of software is a major problem in any software development project. Software engineers develop models that provide early estimates of quality metrics which allow them to take actions against emerging quality problems. The use of a neural network as a tool to classify programs as a low, medium, or high risk for errors or change is explored using multiple software metrics as input. It is demonstrated that a neural network, trained using the back-propagation...
Show moreAccurately classifying the quality of software is a major problem in any software development project. Software engineers develop models that provide early estimates of quality metrics which allow them to take actions against emerging quality problems. The use of a neural network as a tool to classify programs as a low, medium, or high risk for errors or change is explored using multiple software metrics as input. It is demonstrated that a neural network, trained using the back-propagation supervised learning strategy, produced the desired mapping between the static software metrics and the software quality classes. The neural network classification methodology is compared to the discriminant analysis classification methodology in this experiment. The comparison is based on two and three class predictive models developed using variables resulting from principal component analysis of software metrics.
Show less
Date Issued: 1995
PURL: http://purl.flvc.org/fcla/dt/15183
Subject Headings: Computer software--Evaluation, Software engineering, Neural networks (Computer science)
Format: Document (PDF)

Title: CRACKING THE SPARSE CODE: LATERAL COMPETITION FORMS ROBUST V1-LIKE REPRESENTATIONS IN CONVOLUTIONAL NEURAL NETWORKS.
Creator: Teti, Michael, Barenholtz, Elan, Hahn, William, Florida Atlantic University, Center for Complex Systems and Brain Sciences, Charles E. Schmidt College of Science
Abstract/Description: Although state-of-the-art Convolutional Neural Networks (CNNs) are often viewed as a model of biological object recognition, they lack many computational and architectural motifs that are postulated to contribute to robust perception in biological neural systems. For example, modern CNNs lack lateral connections, which greatly outnumber feed-forward excitatory connections in primary sensory cortical areas and mediate feature-specific competition between neighboring neurons to form robust,...
Show moreAlthough state-of-the-art Convolutional Neural Networks (CNNs) are often viewed as a model of biological object recognition, they lack many computational and architectural motifs that are postulated to contribute to robust perception in biological neural systems. For example, modern CNNs lack lateral connections, which greatly outnumber feed-forward excitatory connections in primary sensory cortical areas and mediate feature-specific competition between neighboring neurons to form robust, sparse representations of sensory stimuli for downstream tasks. In this thesis, I hypothesize that CNN layers equipped with lateral competition better approximate the response characteristics and dynamics of neurons in the mammalian primary visual cortex, leading to increased robustness under noise and/or adversarial attacks relative to current robust CNN layers. To test this hypothesis, I develop a new class of CNNs called LCANets, which simulate recurrent, feature-specific lateral competition between neighboring neurons via a sparse coding model termed the Locally Competitive Algorithm (LCA). I first perform an analysis of the response properties of LCA and show that sparse representations formed by lateral competition more accurately mirror response characteristics of primary visual cortical populations and are more useful for downstream tasks like object recognition than previous sparse CNNs, which approximate competition with winner-take-all mechanisms implemented via thresholding.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00014050
Subject Headings: Neural networks (Computer science), Machine learning, Computer vision
Format: Document (PDF)

Title: META-LEARNING AND ENSEMBLE METHODS FOR DEEP NEURAL NETWORKS.
Creator: Liu, Feng, Dingding, Wang, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Deep Neural Networks have been widely applied in many different applications and achieve significant improvement over classical machine learning techniques. However, training a neural network usually requires large amount of data, which is not guaranteed in some applications such as medical image classification. To address this issue, people propose to implement meta learning and ensemble learning techniques to make deep learning trainers more powerful. This thesis focuses on using deep...
Show moreDeep Neural Networks have been widely applied in many different applications and achieve significant improvement over classical machine learning techniques. However, training a neural network usually requires large amount of data, which is not guaranteed in some applications such as medical image classification. To address this issue, people propose to implement meta learning and ensemble learning techniques to make deep learning trainers more powerful. This thesis focuses on using deep learning equipped with meta learning and ensemble learning to study specific problems. We first propose a new deep learning based method for suggestion mining. The major challenges of suggestion mining include cross domain issue and the issues caused by unstructured and highly imbalanced data structure. To overcome these challenges, we propose to apply Random Multi-model Deep Learning (RMDL) which combines three different deep learning architectures (DNNs, RNNs and CNNs) and automatically selects the optimal hyper parameter to improve the robustness and flexibility of the model. Our experimental results on the SemEval-2019 competition Task 9 data sets demonstrate that our proposed RMDL outperforms most of the existing suggestion mining methods.
Show less
Date Issued: 2020
PURL: http://purl.flvc.org/fau/fd/FA00013481
Subject Headings: Neural networks (Computer science), Deep learning, Neural Networks in Applications, Machine learning--Technique
Format: Document (PDF)

Title: Liver Cancer Risk Quantification through an Artificial Neural Network based on Personal Health Data.
Creator: Ataei, Afrouz, Muhammad, Wazir, Florida Atlantic University, Department of Physics, Charles E. Schmidt College of Science
Abstract/Description: Liver cancer is the sixth most common type of cancer worldwide and is the third leading cause of cancer related mortality. Several types of cancer can form in the liver. Hepatocellular carcinoma (HCC) makes up 75%-85% of all primary liver cancers and it is a malignant disease with limited therapeutic options due to its aggressive progression. While the exact cause of liver cancer may not be known, habits/lifestyle may increase the risk of developing the disease. Several risk prediction models...
Show moreLiver cancer is the sixth most common type of cancer worldwide and is the third leading cause of cancer related mortality. Several types of cancer can form in the liver. Hepatocellular carcinoma (HCC) makes up 75%-85% of all primary liver cancers and it is a malignant disease with limited therapeutic options due to its aggressive progression. While the exact cause of liver cancer may not be known, habits/lifestyle may increase the risk of developing the disease. Several risk prediction models for HCC are available for individuals with hepatitis B and C virus infections who are at high risk but not for general population. To address this challenge, an artificial neural network (ANN) was developed, trained, and tested using the health data to predict liver cancer risk. Our results indicate that our ANN can be used to predict liver cancer risk with changes with lifestyle and may provide a novel approach to identify patients at higher risk and can be bene ted from early diagnosis.
Show less
Date Issued: 2021
PURL: http://purl.flvc.org/fau/fd/FA00013742
Subject Headings: Liver--Cancer, Artificial neural networks, Neural networks (Computer science), Cancer--Risk assessment
Format: Document (PDF)

Title: DEEP MAXOUT NETWORKS FOR CLASSIFICATION PROBLEMS ACROSS MULTIPLE DOMAINS.
Creator: Castaneda, Gabriel, Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Machine learning techniques such as deep neural networks have become an indispensable tool for a wide range of applications such as image classification, speech recognition, and sentiment analysis in text. An activation function is a mathematical equation that determines the output of each neuron in the neural network. In deep learning architectures the choice of activation functions is very important to the network’s performance. Activation functions determine the output of the model, its...
Show moreMachine learning techniques such as deep neural networks have become an indispensable tool for a wide range of applications such as image classification, speech recognition, and sentiment analysis in text. An activation function is a mathematical equation that determines the output of each neuron in the neural network. In deep learning architectures the choice of activation functions is very important to the network’s performance. Activation functions determine the output of the model, its computational efficiency, and its ability to train and converge after multiple iterations of training epochs. The selection of an activation function is critical to building and training an effective and efficient neural network. In real-world applications of deep neural networks, the activation function is a hyperparameter. We have observed a lack of consensus on how to select a good activation function for a deep neural network, and that a specific function may not be suitable for all domain-specific applications.
Show less
Date Issued: 2019
PURL: http://purl.flvc.org/fau/fd/FA00013362
Subject Headings: Classification, Machine learning--Technique, Neural networks (Computer science)
Format: Document (PDF)

Title: Enhancement of Deep Neural Networks and Their Application to Text Mining.
Creator: Prusa, Joseph Daniel, Khoshgoftaar, Taghi M., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Many current application domains of machine learning and arti cial intelligence involve knowledge discovery from text, such as sentiment analysis, document ontology, and spam detection. Humans have years of experience and training with language, enabling them to understand complicated, nuanced text passages with relative ease. A text classi er attempts to emulate or replicate this knowledge so that computers can discriminate between concepts encountered in text; however, learning high-level...
Show moreMany current application domains of machine learning and arti cial intelligence involve knowledge discovery from text, such as sentiment analysis, document ontology, and spam detection. Humans have years of experience and training with language, enabling them to understand complicated, nuanced text passages with relative ease. A text classi er attempts to emulate or replicate this knowledge so that computers can discriminate between concepts encountered in text; however, learning high-level concepts from text, such as those found in many applications of text classi- cation, is a challenging task due to the many challenges associated with text mining and classi cation. Recently, classi ers trained using arti cial neural networks have been shown to be e ective for a variety of text mining tasks. Convolutional neural networks have been trained to classify text from character-level input, automatically learn high-level abstract representations and avoiding the need for human engineered features. This dissertation proposes two new techniques for character-level learning, log(m) character embedding and convolutional window classi cation. Log(m) embedding is a new character-vector representation for text data that is more compact and memory e cient than previous embedding vectors. Convolutional window classi cation is a technique for classifying long documents, i.e. documents with lengths exceeding the input dimension of the neural network. Additionally, we investigate the performance of convolutional neural networks combined with long short-term memory networks, explore how document length impacts classi cation performance and compare performance of neural networks against non-neural network-based learners in text classi cation tasks.
Show less
Date Issued: 2018
PURL: http://purl.flvc.org/fau/fd/FA00005959
Subject Headings: Text Mining, Neural networks (Computer science), Machine learning
Format: Document (PDF)

Title: Parallel Distributed Deep Learning on Cluster Computers.
Creator: Kennedy, Robert Kwan Lee, Khoshgoftaar, Taghi M., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Deep Learning is an increasingly important subdomain of arti cial intelligence. Deep Learning architectures, arti cial neural networks characterized by having both a large breadth of neurons and a large depth of layers, bene ts from training on Big Data. The size and complexity of the model combined with the size of the training data makes the training procedure very computationally and temporally expensive. Accelerating the training procedure of Deep Learning using cluster computers faces...
Show moreDeep Learning is an increasingly important subdomain of arti cial intelligence. Deep Learning architectures, arti cial neural networks characterized by having both a large breadth of neurons and a large depth of layers, bene ts from training on Big Data. The size and complexity of the model combined with the size of the training data makes the training procedure very computationally and temporally expensive. Accelerating the training procedure of Deep Learning using cluster computers faces many challenges ranging from distributed optimizers to the large communication overhead speci c to a system with o the shelf networking components. In this thesis, we present a novel synchronous data parallel distributed Deep Learning implementation on HPCC Systems, a cluster computer system. We discuss research that has been conducted on the distribution and parallelization of Deep Learning, as well as the concerns relating to cluster environments. Additionally, we provide case studies that evaluate and validate our implementation.
Show less
Date Issued: 2018
PURL: http://purl.flvc.org/fau/fd/FA00013080
Subject Headings: Deep learning., Neural networks (Computer science)., Artificial intelligence., Machine learning.
Format: Document (PDF)

Title: Neural network system for operations management.
Creator: Ezziane, Zoheir Hocine., Florida Atlantic University, Mazouz, Abdel Kader, College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
Abstract/Description: Distribution centers and warehouses are becoming more and more dependent on advanced computer technologies to establish and maintain competitiveness in a global economy. Neural network represent a new technology with a wide scope of potential warehouses applications, ranging from planning and forecasting to overall performance. In this dissertation, numerous results are showing increases in warehouse performance, when using neural network technology. The neural network system is used as a...
Show moreDistribution centers and warehouses are becoming more and more dependent on advanced computer technologies to establish and maintain competitiveness in a global economy. Neural network represent a new technology with a wide scope of potential warehouses applications, ranging from planning and forecasting to overall performance. In this dissertation, numerous results are showing increases in warehouse performance, when using neural network technology. The neural network system is used as a forecasting tool. It is then compared to time series forecasting analysis. The comparison process is designed to increase the warehouse performance understudy. At the end of this process, the results are forecasting variables needed to eventually increase warehouse performance and efficiency. Initially, neural networks along with time series are used to make the forecast on inventory control. Then the following step is to let different neural network modules perform the forecasting analysis on other management operations like inventory adjustments, accuracy and turnover, customer complaints and labor productivity for any distribution center or warehouse. The concept of benchmarking is also used, in order to provide tools which will help warehouse management determining performance levels for each subcomponent of the warehouse operations, and consequently the overall performance of the warehouse or distributor center taken into consideration after feeding in the appropriate data to the system.
Show less
Date Issued: 1994
PURL: http://purl.flvc.org/fcla/dt/12369
Subject Headings: Operations research, Warehouses, Neural networks (Computer science)--Industrial applications
Format: Document (PDF)

Title: PRGMDH algorithm for neural network development and its applications.
Creator: Tangadpelli, Chetan., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: The existing Group Method of Data Handling (GMDH) algorithm has characteristics that are ideal for neural network design. This thesis introduces a new algorithm that applies some of the best characteristics of GMDH to neural network design and develops a Pruning based Regenerated Network by discarding the neurons in a layer which don't contribute for the creation of neurons in next layer. Unlike other conventional algorithms, which generate a network which is a black box, the new algorithm...
Show moreThe existing Group Method of Data Handling (GMDH) algorithm has characteristics that are ideal for neural network design. This thesis introduces a new algorithm that applies some of the best characteristics of GMDH to neural network design and develops a Pruning based Regenerated Network by discarding the neurons in a layer which don't contribute for the creation of neurons in next layer. Unlike other conventional algorithms, which generate a network which is a black box, the new algorithm provides visualization of the network displaying all the neurons in the network. The algorithm is general enough that it will accept any number of inputs and any sized training set. To show the flexibility of the Pruning based Regenerated Network, this algorithm is used to analyze different combinations of drugs and determine which pathways in these networks interact and determine the combination of drugs that take advantage of these interactions to maximize a desired effect on genes.
Show less
Date Issued: 2006
PURL: http://purl.flvc.org/fcla/dt/13397
Subject Headings: Neural networks (Computer science), GMDH algorithms, Pattern recognition systems
Format: Document (PDF)

Title: Performance analysis of back propagation algorithm using artificial neural networks.
Creator: Malladi, Sasikanth., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Backpropagation is a standard algorithm that is widely employed in many neural networks. Due to its wide acceptance and implementation, a standard benchmark for evaluating the performance of the algorithm is a handy tool for software design and development. The object of this thesis is to propose the use of the classic XOR problem for the performance evaluation of the backpropagation algorithm, with some variations on the input data sets. This thesis covers background work in this area and...
Show moreBackpropagation is a standard algorithm that is widely employed in many neural networks. Due to its wide acceptance and implementation, a standard benchmark for evaluating the performance of the algorithm is a handy tool for software design and development. The object of this thesis is to propose the use of the classic XOR problem for the performance evaluation of the backpropagation algorithm, with some variations on the input data sets. This thesis covers background work in this area and discusses the results obtained by other researchers. A series of test cases are then developed and run to perform the performance analysis of the backpropagation algorithm. As the performance of the networks depends strongly on the inputs, the effect of variation of the design parameters for the networks are evaluated and discussed.
Show less
Date Issued: 2002
PURL: http://purl.flvc.org/fcla/dt/12961
Subject Headings: Back propagation (Artificial intelligence), Neural networks (Computer science)
Format: Document (PDF)

Title: Path selection through a three-stage switching network using neural networks.
Creator: Keskiner, Haluk., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Several neural network applications solving practical problems in communications are presented. A neural network algorithm to select paths through a three stage switching network is developed. An analysis of the dynamics of the neural network and a convergence proof are provided. With the help of computer simulations, a four dimensional region for the valid combinations of the neural network parameters was discovered. An analysis is performed to determine the characteristics of this region....
Show moreSeveral neural network applications solving practical problems in communications are presented. A neural network algorithm to select paths through a three stage switching network is developed. An analysis of the dynamics of the neural network and a convergence proof are provided. With the help of computer simulations, a four dimensional region for the valid combinations of the neural network parameters was discovered. An analysis is performed to determine the characteristics of this region. The behavior of the neural network algorithm for different switching network configurations and varying traffic patterns were investigated. The effect of initial state of the neural network and heuristic improvements to the algorithm is provided. A comparative analysis of the neural network path selection algorithm against a sequential search method is also given.
Show less
Date Issued: 1991
PURL: http://purl.flvc.org/fcla/dt/14741
Subject Headings: Neural networks (Computer science), Packet switching (Data transmission)
Format: Document (PDF)

Title: Obstacle avoidance for AUVs.
Creator: Gan, (Linda) Huilin., Florida Atlantic University, Ganesan, Krishnamurthy
Abstract/Description: This thesis describes a general three-dimensional Obstacle Avoidance approach for the Autonomous Underwater Vehicle (AUV) using a forward-looking high-frequency active sonar system. This approach takes into account obstacle distance and AUV speed to determine the vehicle's heading, depth and speed. Fuzzy logic has been used to avoid the abrupt turn of the AUV in the presence of obstacles so that the vehicle can maneuver smoothly in the underwater environment. This approach has been...
Show moreThis thesis describes a general three-dimensional Obstacle Avoidance approach for the Autonomous Underwater Vehicle (AUV) using a forward-looking high-frequency active sonar system. This approach takes into account obstacle distance and AUV speed to determine the vehicle's heading, depth and speed. Fuzzy logic has been used to avoid the abrupt turn of the AUV in the presence of obstacles so that the vehicle can maneuver smoothly in the underwater environment. This approach has been implemented as an important part of the overall AUV software system. Using this approach, multiple objects could be differentiated automatically by the program through analyzing the sonar returns. The current vehicle state and the path of navigation of the AUV are self-adjusted depending on the location of the obstacles that are detected. A minimum safety distance is always maintained between the AUV and any object. Extensive testing of the program has been performed using several simulated AUV on-board systems undergoing different types of missions.
Show less
Date Issued: 1997
PURL: http://purl.flvc.org/fcla/dt/15451
Subject Headings: Submersibles--Automatic control, Fuzzy logic, Neural networks (Computer science)
Format: Document (PDF)

Title: Sediment layer tracking using neural networks.
Creator: Freyermuth, Vincent Nicolas., Florida Atlantic University, Schock, Steven G.
Abstract/Description: The detection of sediment layer interfaces in normal incidence acoustic reflection data is a requirement for automatic classification and geologic mapping of subsurface layers. The detection is difficult because of the constructive and destructive interference caused by the impedance changes in the sediment column and high scattering noise levels. The purpose of this work is to implement a procedure using neural networks that automatically detects the sediment layers from the envelope of...
Show moreThe detection of sediment layer interfaces in normal incidence acoustic reflection data is a requirement for automatic classification and geologic mapping of subsurface layers. The detection is difficult because of the constructive and destructive interference caused by the impedance changes in the sediment column and high scattering noise levels. The purpose of this work is to implement a procedure using neural networks that automatically detects the sediment layers from the envelope of acoustic reflections. The data was collected using a sub-bottom profiler that transmits a 2 to 10 kHz FM pulse. The detection procedure is a three step method: a first neural network removes most of the reflections due to random scatterers, a second neural network tracks the layers and a third algorithm recognizes the segments of detected layers corresponding to the same sediment interface Applied on different sub-bottom images, the procedure detects more than 80% of the layers correctly.
Show less
Date Issued: 1998
PURL: http://purl.flvc.org/fcla/dt/15561
Subject Headings: Neural networks (Computer science), Marine sediments--Acoustic properties
Format: Document (PDF)

Title: A case study: Performance enhancement of nonlinear combinational optimization problem by neural networks.
Creator: Soni, Saurabh., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Artificial Neural Networks have been widely used for obtaining solutions for combinational optimization problems. Traveling Salesman problem is a well known nonlinear combinational optimization problem. In Traveling Salesman problem, a fixed number of cities is given. An optimal tour of all these cities is required such that each city is visited only once and the total tour distance to be covered has to be minimized. Hopfield Networks have been applied for generating an optimal solution....
Show moreArtificial Neural Networks have been widely used for obtaining solutions for combinational optimization problems. Traveling Salesman problem is a well known nonlinear combinational optimization problem. In Traveling Salesman problem, a fixed number of cities is given. An optimal tour of all these cities is required such that each city is visited only once and the total tour distance to be covered has to be minimized. Hopfield Networks have been applied for generating an optimal solution. However there are certain factors which result in instability and local optimization of Hopfield Networks. In such cases the solutions obtained may not be optimal and feasible. In this thesis, the application of the K-Means algorithm is combined with the Hopfield Networks to generate more stable and optimum solutions to traveling salesperson problem.
Show less
Date Issued: 2004
PURL: http://purl.flvc.org/fcla/dt/13108
Subject Headings: Neural networks (Computer science), Traveling-salesman problem
Format: Document (PDF)

Neural networks (Computer science) (79)	+ -
Artificial intelligence (10)	+ -
Pattern recognition systems (9)	+ -
Machine learning (7)	+ -
Fuzzy logic (6)	+ -

Deep learning (Machine learning) (5)	+ -
GMDH algorithms (5)	+ -
Computer algorithms (4)	+ -
Image processing (4)	+ -
Time-series analysis (4)	+ -
Back propagation (Artificial intelligence) (3)	+ -
Genetic algorithms (3)	+ -
Packet switching (Data transmission) (3)	+ -
Software engineering (3)	+ -
Submersibles--Automatic control (3)	+ -
Artificial intelligence. (2)	+ -
Artificial neural networks (2)	+ -
Asynchronous transfer mode (2)	+ -
Cognitive neuroscience. (2)	+ -
Computer vision (2)	+ -
Convolutional neural networks (2)	+ -
Deep Learning (2)	+ -
Machine learning--Technique (2)	+ -
Optical character recognition devices (2)	+ -
Pavements--Skid resistance (2)	+ -
Reinforcement learning (2)	+ -
Stock price forecasting (2)	+ -
System identification (2)	+ -
Adaptive control systems--Computer simulation (1)	+ -
Air--Pollution--Florida--Palm Beach County (1)	+ -

Florida Atlantic University (78)	+ -
College of Engineering and Computer Science (57)	+ -
Department of Computer and Electrical Engineering and Computer Science (48)	+ -
Pandya, Abhijit S. (22)	+ -
Charles E. Schmidt College of Science (14)	+ -

Department of Ocean and Mechanical Engineering (8)	+ -
Khoshgoftaar, Taghi M. (7)	+ -
Barenholtz, Elan (6)	+ -
Center for Complex Systems and Brain Sciences (5)	+ -
Neelakanta, Perambur S. (5)	+ -
Department of Physics (4)	+ -
Department of Mathematical Sciences (3)	+ -
Muhammad, Wazir (3)	+ -
De Groff, Dolores F. (2)	+ -
Department of Psychology (2)	+ -
Furht, Borko (2)	+ -
Hahn, William (2)	+ -
Jirsa, Viktor K. (2)	+ -
Marques, Oge (2)	+ -
Scarlatos, Panagiotis (Pete) D. (2)	+ -
Shankar, Ravi (2)	+ -
Sudhakar, Raghavan (2)	+ -
Zhuang, Hanqi (2)	+ -
Zilouchian, Ali (2)	+ -
Abusalah, Salahalddin Tawfiq. (1)	+ -
Akbarian, Hamid (1)	+ -
An, Edgar (1)	+ -
Andrews, Whitney Angelica Johanna (1)	+ -
Ataei, Afrouz (1)	+ -
Banerjee, Arpan (1)	+ -

Document (PDF) (84)	+ -
Set of related objects (1)	+ -

Search In

Pages

Pages

Sort Results By:

Narrow results by:

Collection

Topical Subject

Genre

Type of Resource

Language

Creator

Format

Owner